© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 220553
    Prev
    Next
    INDEX
    Explanations

    gold, good, European, dark

    np_acts-logits-general · gemini-2.5-flash-lite

    Exchange Rates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    т
    0.58
    h
    0.55
    m
    0.53
    м
    0.51
     ので
    0.50
    v
    0.48
    ம்
    0.48
    ac
    0.46
    ih
    0.46
    achable
    0.46
    POSITIVE LOGITS
     Entrada
    0.49
    गैर
    0.48
     Recursos
    0.47
    䂺
    0.46
    ça
    0.46
    ريق
    0.45
    ravés
    0.44
     entrada
    0.44
    utenção
    0.43
    鈽
    0.43
    Activations Density 0.000%

    No Known Activations